Proceedings
Authors
| Filter results4 paper(s) found. |
|---|
1. Challenges and Successes when Generating In-season Multi-temporal Calibrated Aerial ImageryDigital aerial imagery (DAI) of the crop canopy collected by aircraft and unmanned aerial vehicles is the yardstick of precision agriculture. However, the quantitative use of this imagery is often limited by its variable characteristics, low quality, and lack of radiometric calibration. To increase the quality and utility of using DAI in crop management, it is important to evaluate and address these limitations of DAI. Even though there have been improvements in spatial resolution... P.M. Kyveryga, J. Pritsolas, J. Connor, R. Pearson |
2. Within-field Profitability Assessment: Impact of Weather, Field Management and SoilsProfitability in crop production is largely driven by crop yield, production costs and commodity prices. The objective of this study was to quantify the often substantial yet somewhat illusive impact of weather, management, and soil spatial variability on within-field profitability in corn and soybean crop production using profitability indices for profit (net return) and return-on-investment (ROI) to produce estimates. We analyzed yield and cropping system data provided by 42 farmers within Central... P.M. Kyveryga, S. Fey, J. Connor, A. Kiel, D. Muth |
3. Exploring Tractor Mounted Hyperspectral System Ability to Detect Sudden Death Syndrome Infection and Assess Yield in SoybeanPre-visual detection of crop disease is critical for both food and economic security. The sudden death syndrome (SDS) in soybeans, caused by Fusarium virguliforme (Fv), induces 100 million US$ crop loss, per year, in the US alone. Field-based spectroscopic remote sensing offers a method to enable timely detection, but still requires appropriate instrumentation and testing. Soybean plants were measured at canopy level over a course of a growing season to assess the capacity of spectral measurements... I. Herrmann, S. Vosberg, P. Ravindran, A. Singh, P. Townsend, S. Conley |
4. 3D Computer Vision with a Spatial-temporal Neural Network for Lameness Detection of SowsThe lameness of sows is one of the biggest concerns for swine producers, which can lead to considerable economic losses due to reduced productivity and welfare. There is a real need for early detection of lameness in sows to enable timely intervention and minimize loss. Currently, lame detection relies on visual observation and locomotion scoring of sows, which is subjective, labor-intensive, and difficult to conduct for large groups of animals within a short time. This study presents 3D computer... Y. Wang, Y. Lu, D. Morris, M. Benjamin, M. Lavagnino, J. Mcintyre |